Machine Learning Models to Predict Phenotype-Associated DNA Sequence Variation in Algae and Humans
Principal Investigator: Charles Danko
DESCRIPTION (provided by applicant):
In the era of genomics and big data, understanding how to use genomic information to predict outcomes is key to advancing the Department of Energy’s biology mission to ‘achieve a predictive understanding of complex biological, earth and environmental systems’ using synthetic biology. This proposal seeks to research and develop machine learning methods to predict the relationship between DNA sequences, gene expression and physiological outcomes. This work would both allow prediction of outcomes across biological systems based on their genome, and shed insight on how genome modification might affect these outcomes.